文件

Structures actionable improvement recommendations to transform code from current state to 10/10 quality. Use when creating improvement plans, prioritizing technical debt, building remediation roadmaps, or after code quality assessments.

Provides type-safe database access with Prisma ORM including schema definition, migrations, queries, and relations. Use when setting up database connections, defining data models, writing queries, or managing database migrations.

Use when writing SQL queries, optimizing database performance, or analyzing data

Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.

自动分析 GitHub 仓库，获取并整理 README、文档、Issues、GitHub Actions、Releases 等所有重要信息，由 LLM 进行深度分析并生成智能 HTML 报告。

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

Automated testing workflow for backend and frontend. Use when writing tests, fixing test failures, or validating code changes. Runs pytest for backend and jest/vitest for frontend.

Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies

Verify claims against referenced sources. Checks if blog content accurately represents external resources, APIs, or documentation.Trigger phrases: "fact check", "verify", "check claims", "verify claims", "check sources", "verify sources"

"What is REALLY at stake here? And for whom?" - STOP. When the matter involves trustworthiness, purchasing decisions, "which is better or more reliable", brand comparisons, marketing claims, corporate behavior, "convince me otherwise", or post-purchase "was this good?" - USE THIS. For technical specs affecting quality (TLC vs QLC, component sourcing) use Light Touch mode. Search and verify even if you think you know. Does NOT trigger for: what to watch/eat/wear, how-to instructions, when/where/who founded, or explicit "just tell me quick."

PolicyEngine code writing style guide - formula optimization, direct returns, eliminating unnecessary variables

Guide for writing unit tests with Vitest for Fastify plugins and routes. Use when creating or modifying tests in app/tests/.

Master ES6+ features including async/await, destructuring, spread operators, arrow functions, promises, modules, iterators, generators, and functional programming patterns for writing clean, efficient JavaScript code. Use when refactoring legacy code, implementing modern patterns, or optimizing JavaScript applications.

Seurat documentation (local mirror)

Interactive ClaudeShack ecosystem initialization that analyzes your codebase, mines history, discusses findings with you to establish baseline understanding, and seeds Oracle with verified knowledge. Use when setting up ClaudeShack in a new project or resetting knowledge. Creates a personalized foundation that improves over use. Sets up Context7 for current library docs.

Generate production-ready React/TypeScript components from detailed specifications with complete tests, styles, and documentation

Create comprehensive implementation plans for engineers with minimal codebase knowledge. This skill should be used when breaking down features into detailed, step-by-step implementation guides following TDD principles.

Multi-phase research orchestration for thorough codebase, documentation, and external knowledge investigation. Invoked by /ai-eng/research command. Use when conducting deep analysis, exploring codebases, investigating patterns, or synthesizing findings from multiple sources.

Create and edit markdown-based presentations using Slidev framework. Use when the user asks to create slides, presentations, or decks, or when working with .slides.md files. Supports mise/bun workflow, GitHub Pages publishing, and multi-deck landing pages.

This skill should be used when evaluating the quality of book chapters, lessons, or educational content. It provides a systematic 6-category rubric with weighted scoring (Technical Accuracy 30%, Pedagogical Effectiveness 25%, Writing Quality 20%, Structure & Organization 15%, AI-First Teaching 10%, Constitution Compliance Pass/Fail) and multi-tier assessment (Excellent/Good/Needs Work/Insufficient). Use this during iterative drafting, after content completion, on-demand review requests, or before validation phases.